Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.8587. Min Act: -0.1700
Data Index: 1480116 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.8587. Min Act: -0.1700
Data Index: 1987277 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.6087. Min Act: -0.1700
Data Index: 1147438 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.4837. Min Act: -0.1700
Data Index: 4742340 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.4837. Min Act: -0.1700
Data Index: 1774125 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.4837. Min Act: -0.1700
Data Index: 2497462 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.4212. Min Act: -0.1700
Data Index: 8266748 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.2962. Min Act: -0.1700
Data Index: 3463960 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.3587. Min Act: -0.1700
Data Index: 351000 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.2337. Min Act: -0.1700
Data Index: 361602 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1087. Min Act: -0.1700
Data Index: 4725291 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1712. Min Act: -0.1700
Data Index: 3123449 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1712. Min Act: -0.1700
Data Index: 361603 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1087. Min Act: -0.1700
Data Index: 6443822 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1087. Min Act: -0.1700
Data Index: 5555658 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.1087. Min Act: -0.1700
Data Index: 1816555 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.0462. Min Act: -0.1700
Data Index: 6496394 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.0462. Min Act: -0.1700
Data Index: 7634053 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8587. Min Range: -9.8587
Max Act: 9.0462. Min Act: -0.1700
Data Index: 6378202 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8587. Min Range: -9.8587
Max Act: 8.9837. Min Act: -0.1700
Data Index: 6099062 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19